© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 184873
    Prev
    Next
    INDEX
    Explanations

    When entering

    np_acts-logits-general · gemini-2.5-flash-lite

    Primary Material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Certains
    0.45
    true
    0.42
     whatnot
    0.42
    tic
    0.41
    {}{
    0.41
    ych
    0.40
    idi
    0.40
    essoas
    0.40
     fermionic
    0.40
    細菌
    0.39
    POSITIVE LOGITS
     supposition
    0.48
     요구
    0.47
     относя
    0.46
     unheard
    0.45
     Water
    0.44
     kurzer
    0.44
    관
    0.43
    纲
    0.43
     Hush
    0.42
     WATER
    0.42
    Activations Density 0.002%

    No Known Activations